New media cultural heritage interactive propagation method and system based on digital twinning

Abstract

The invention discloses a new media cultural heritage interactive transmission method and system based on digital twinning, and relates to the field of cultural transmission, and the method comprises the steps: building a model based on virtual heritage through 3D scanning data of cultural heritage, so as to generate cultural heritage virtual data; the cultural heritage virtual data and the user operation data are input into an augmented reality interaction model to generate virtual touring data, and the virtual touring data comprise cultural heritage virtual data and virtual guide data corresponding to the touring position of a target user; and sending the virtual touring data to an experience end corresponding to the target user, so that the target user performs virtual touring.

Description

Technical Field

[0001] This specification relates to the field of cultural communication, and more specifically, the present application relates to a new media cultural heritage interactive communication method and system based on digital twins. Background Art

[0002] With the advancement of science and technology and the development of extended reality (XR) technologies such as virtual reality (VR) and augmented reality (AR), the digital preservation and virtual display of cultural heritage has gradually become a hot research field. The traditional way of protecting and disseminating cultural heritage mainly relies on on-site displays and museum exhibitions. Visitors need to go to the site in person to experience the true charm of cultural heritage. However, this method is limited by geographical location, time and protection conditions, and cannot allow more people to understand and access these precious historical heritages conveniently and quickly.

[0003] In order to solve these problems, virtual tour technology came into being, digitizing cultural heritage and displaying cultural heritage through computer-generated three-dimensional models and virtual reality technology, breaking the limitations of time and space. However, the existing virtual tour system has the following problems:

[0004] Limited digitization: Many virtual displays are limited to static images or rough three-dimensional models, lacking accurate presentation of cultural heritage details and unable to allow users to fully perceive the artistic and historical value of cultural heritage.

[0005] Insufficient interactive experience: Although some virtual tour systems can simulate the appearance of cultural heritage, they lack rich interactivity. It is difficult for users to gain in-depth understanding of the background information of cultural heritage through virtual tours, and the interactive operations are single, making it difficult to provide an immersive experience.

[0006] Lack of personalized guides: Most existing virtual tours use fixed guide paths and are unable to make personalized recommendations based on users’ operating habits or points of interest, making it difficult to meet the diverse needs of different users. Summary of the invention

[0007] A series of simplified concepts are introduced in the Summary of the Invention section, which will be further described in detail in the Detailed Description of the Invention section. The Summary of the Invention section of this application does not mean to attempt to define the key features and essential technical features of the claimed technical solution, nor does it mean to attempt to determine the scope of protection of the claimed technical solution.

[0008] In the first aspect, the present application proposes a new media cultural heritage interactive communication method based on digital twins, the method comprising: Use the 3D scanning data of cultural heritage to build a model based on virtual heritage to generate virtual data of cultural heritage; Inputting the cultural heritage virtual data and the user operation data into the augmented reality interaction model to generate virtual tour data, wherein the virtual tour data includes the cultural heritage virtual data and the virtual tour guide data corresponding to the target user's tour location; The virtual tour data is sent to an experience terminal corresponding to a target user, so that the target user can conduct a virtual tour.

[0009] In a feasible implementation manner, inputting the cultural heritage virtual data and user operation data into an augmented reality interaction model to generate virtual tour data includes: Mapping the cultural heritage data in the virtual space according to the user's current location information to extract the cultural heritage data within a preset distance of the user's current location; Adjusting the virtual tour content based on the user's interactive operation, wherein the interactive operation includes hand operation and perspective rotation operation; The virtual tour data is generated according to the adjusted virtual tour content and the data of interest.

[0010] In a feasible implementation, it also includes: Classifying the cultural heritage virtual data based on cultural type information through adaptive resonance theory to obtain multiple categories of cultural heritage sub-virtual data, wherein the cultural heritage sub-virtual data includes historical building virtual data, historical musical instrument virtual data and mural virtual data; Sending all the cultural heritage sub-virtual data to the client of the corresponding cultural category research institution, so that the corresponding cultural category research institution performs cultural research operations and generates heritage extension research data; Sending all the cultural heritage sub-virtual data to the online forum community of the corresponding cultural category, so that the online forum community of the corresponding cultural category can discuss and perform secondary creation operations, and generate heritage extension creation data; All of the cultural heritage sub-virtual data are sent to the intelligent generation model of the corresponding cultural category, so that the intelligent generation model of the corresponding cultural category performs a recommended video generation operation and generates heritage extension recommendation data.

[0011] In a feasible implementation manner, the method of enabling the corresponding cultural research institution to perform cultural research operations and generate heritage extension research data includes: Obtain information on the characteristics of the cultural knowledge base of research institutions; Extracting cultural element information of various types of cultural heritage sub-virtual data using natural language processing and entity recognition methods; Constructing a related knowledge graph based on the cultural knowledge base feature information and the cultural element information; Generate basic extended data through the TransE / TransH reasoning algorithm according to the associated knowledge graph; The heritage extended research data is generated based on rule reasoning according to the basic extended data to update the cultural knowledge base of the research institution.

[0012] In a feasible implementation manner, enabling the online forum community of the corresponding cultural category to conduct discussions and secondary creation operations and generate heritage extension creation data includes: Acquire the uploaded information of the online community user, wherein the uploaded information includes text description information, sketch information and initial creative material information; Based on the uploaded information and the cultural heritage sub-virtual data, a generative adversarial network model is used to perform a preset number of training and optimization operations to generate heritage extension creation data.

[0013] In a feasible implementation manner, the method of enabling the intelligent generation model of the corresponding cultural category to perform a recommended video generation operation and generate heritage extension recommendation data includes: Get the hot tag information corresponding to the current hot video information; Get current holiday information; Calculate the correlation information of each type of cultural heritage sub-virtual data according to the hot tag information and the current holiday information; Determine the cultural heritage sub-virtual data whose correlation information is greater than a preset correlation as the creation source data; The creation source data, the hot tag information and the current holiday information are input into a target Transformer model to generate the heritage extension recommendation data.

[0014] In a feasible implementation, it also includes: Performing intelligent evaluation on the heritage extension creation data and the heritage extension recommendation data to obtain an evaluation result; The heritage extension creation data and the heritage extension recommendation data whose evaluation results are greater than a preset result level are sent to an interactive terminal of a corresponding cultural tourist area.

[0015] In a feasible implementation manner, the intelligently evaluating the heritage extension creation data and the heritage extension recommendation data to obtain an evaluation result includes: Determine an evaluation result of the extended creation based on the artistic score, historical consistency score and creativity score of the heritage extended creation data; Determine an extension recommendation evaluation result based on the relevance score, user feedback score and audience coverage score of the heritage extension recommendation data; The evaluation result is determined based on the extension creation evaluation result and the extension recommendation evaluation result.

[0016] In a feasible implementation manner, the specific steps of determining the interactive terminal corresponding to the cultural tourist area include: Obtain user location information, cultural heritage area map data, interactive terminal location data, user preference data, and user preferred interaction method data; The interactive terminal corresponding to the cultural sightseeing area is determined based on the user location information, the cultural heritage area map data, the interactive terminal location data, the user preference data and the user preferred interaction mode data.

[0017] In the second aspect, the present application proposes a new media cultural heritage interactive communication system based on digital twins, comprising: A first generating unit is used to construct a model based on the virtual heritage using the 3D scanning data of the cultural heritage to generate virtual data of the cultural heritage; A second generating unit inputs the cultural heritage virtual data and the user operation data into an augmented reality interaction model to generate virtual tour data, wherein the virtual tour data includes the cultural heritage virtual data and virtual guide data corresponding to the target user's tour location; The interactive control unit is used to send the virtual tour data to the experience terminal corresponding to the target user, so that the target user can perform a virtual tour.

[0018] In summary, the present application uses 3D scanning technology and virtual heritage construction models to accurately digitize cultural heritage and generate virtual data that highly restores the details of cultural heritage. This technology can not only show the appearance of cultural heritage, but also present the texture, material and structure of cultural heritage in detail. Users can observe the tiny details in cultural heritage at close range, which improves the accuracy and realism of virtual display. Compared with the rough three-dimensional model in traditional virtual display, the present application enables users to obtain a more realistic cultural experience in a virtual environment. By inputting cultural heritage virtual data and user operation data into the augmented reality interaction model, the present application can dynamically generate virtual tour data according to the user's real-time operation behavior. This means that every operation of the user will trigger the system to adjust the displayed content, and the user can freely explore the cultural heritage area of ​​interest without following a fixed guide path. Compared with traditional virtual tours, the present application gives users greater autonomy, making the tour more flexible and more personalized, meeting the diverse needs of users. The virtual tour data generated by the present application not only includes the cultural heritage model corresponding to the user's current location, but also includes rich virtual tour data, such as historical background, cultural relics interpretation, audio tour, etc. Users can obtain cultural heritage information related to the current tour location in real time through the experience-end device, and realize the immersive experience of "tour and learn". At the same time, the augmented reality interaction model supports a variety of interactive methods. Users can interact with virtual cultural heritage through gesture control, voice commands, touch operations, etc., which further enhances the fun and interactivity of the tour. This application designs a virtual tour function on the experience end, which is suitable for different types of terminal devices, including AR glasses, VR headsets, other XR devices and mobile devices, etc. Users can conduct virtual tours anytime and anywhere according to their own equipment conditions. This not only breaks the limitations of geography and time, but can also be applied to multiple scenarios, such as online exhibitions of museums, cultural courses of educational institutions, virtual tours of tourist attractions, etc., providing more possibilities for the dissemination and protection of cultural heritage. This application can adjust the display content of the system according to the historical data and behavioral preferences of user operations, and provide a tour path that better meets user needs. At the same time, the system can dynamically update the virtual data of cultural heritage, so that users can always obtain the latest cultural heritage information. This flexible feedback mechanism can effectively improve user satisfaction and experience, and has obvious advantages over traditional static virtual tour methods. This application achieves highly accurate digitization of cultural heritage through 3D scanning and virtual data construction of cultural heritage; through augmented reality interactive models and virtual tour data generation, it provides users with an immersive, personalized and interactive virtual cultural heritage experience. Compared with existing virtual tour technologies, this application solves problems such as insufficient display accuracy, insufficient interactivity, and poor personalization, significantly improves the digital communication effect of cultural heritage, and provides new technical paths and application scenarios for the protection and inheritance of cultural heritage. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present specification. Also, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings: Figure 1 A schematic diagram of the process of a new media cultural heritage interactive communication method based on digital twins provided in an embodiment of the present application; Figure 2 A schematic diagram of the structure of a new media cultural heritage interactive communication system based on digital twins provided in an embodiment of the present application. DETAILED DESCRIPTION

[0020] The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of this application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices. The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments.

[0021] See also Figure 1 , which is a schematic diagram of the process of a new media cultural heritage interactive communication method based on digital twins provided in an embodiment of the present application, which may specifically include: S110, constructing a model based on the 3D scanning data of the cultural heritage based on the virtual heritage to generate virtual data of the cultural heritage; For example, 3D scanning data of cultural heritage is obtained through advanced scanning equipment (such as laser scanning, photogrammetry technology, etc.), covering the appearance, structure, texture and other details of cultural heritage. The high-precision collection of these data ensures that the authenticity and details of cultural heritage are accurately presented.

[0022] These 3D scan data are then input into the "Virtual Heritage Construction Model", which is an algorithm or program specifically designed to convert cultural heritage from the physical world into digital form. In this process, the model will analyze and process the 3D scan data to generate a digital 3D model of the cultural heritage, namely "cultural heritage virtual data". These virtual data can simulate the appearance and structure of cultural heritage in a digital environment and provide a basis for subsequent steps. For example: the 3D scan data of an ancient building can be converted into virtual data through the Virtual Heritage Construction Model, allowing users to see every detail of the building in the virtual space, even tiny decorations and textures that cannot be directly observed by the naked eye.

[0023] S120, inputting the cultural heritage virtual data and the user operation data into the augmented reality interaction model to generate virtual tour data, wherein the virtual tour data includes the cultural heritage virtual data and virtual tour guide data corresponding to the target user's tour location; Exemplarily, the digital cultural heritage model generated above contains three-dimensional information and other digital features of the cultural heritage. User operation data includes the interactive behaviors generated by users during the virtual tour, such as the places chosen by users to visit, the interactive methods, and the content requirements of the virtual tour. User operation data can be collected in real time by experience-end devices (such as AR glasses and mobile devices), such as the trajectory of users' movement in the virtual space, the hot spots clicked, etc. Augmented reality interaction model: It is a computing model that can integrate user operation data and virtual data of cultural heritage. It can dynamically generate a virtual tour experience that matches the user's behavior. For example, when a user chooses to "approach" a cultural heritage in a virtual environment, the augmented reality interaction model will load the corresponding virtual data according to the user's location, and display detailed information of the location, such as the internal structure of the building, historical background, etc.

[0024] S130: Send the virtual tour data to an experience terminal corresponding to the target user, so that the target user can perform a virtual tour.

[0025] Exemplarily, the virtual tour data generated by the augmented reality interaction model is sent to the user's device in real time through the network or other transmission methods. The device may be, but is not limited to, AR glasses, VR headsets, other XR devices, and mobile devices. The user receives and presents the virtual tour data through the experience-end device, and the user can freely explore the cultural heritage in a virtual environment. The experience end can support a variety of interaction methods, such as operating the cultural heritage virtual data through gesture control, voice commands, or touch screen clicks, exploring different areas, or obtaining more background information. This process ensures that users have an immersive cultural heritage experience. Although they are not on site, they can still visit the cultural heritage as if they were there and obtain rich guide information.

[0026] In summary, the present application uses 3D scanning technology and virtual heritage construction models to accurately digitize cultural heritage and generate virtual data that highly restores the details of cultural heritage. This technology can not only show the appearance of cultural heritage, but also present the texture, material and structure of cultural heritage in detail. Users can observe the tiny details in cultural heritage at close range, which improves the accuracy and realism of virtual display. Compared with the rough three-dimensional model in traditional virtual display, the present application enables users to obtain a more realistic cultural experience in a virtual environment. By inputting cultural heritage virtual data and user operation data into the augmented reality interaction model, the present application can dynamically generate virtual tour data according to the user's real-time operation behavior. This means that every operation of the user will trigger the system to adjust the displayed content, and the user can freely explore the cultural heritage area of ​​interest without following a fixed guide path. Compared with traditional virtual tours, the present application gives users greater autonomy, making the tour more flexible and more personalized, meeting the diverse needs of users. The virtual tour data generated by the present application not only includes the cultural heritage model corresponding to the user's current location, but also includes rich virtual tour data, such as historical background, cultural relics interpretation, audio tour, etc. Users can obtain cultural heritage information related to the current tour location in real time through the experience-end device, and realize the immersive experience of "tour and learn". At the same time, the augmented reality interaction model supports a variety of interactive methods. Users can interact with virtual cultural heritage through gesture control, voice commands, touch operations, etc., which further enhances the fun and interactivity of the tour. This application designs a virtual tour function on the experience end, which is suitable for different types of terminal devices, including AR glasses, VR headsets, other XR devices and mobile devices, etc. Users can conduct virtual tours anytime and anywhere according to their own equipment conditions. This not only breaks the limitations of geography and time, but can also be applied to multiple scenarios, such as online exhibitions of museums, cultural courses of educational institutions, virtual tours of tourist attractions, etc., providing more possibilities for the dissemination and protection of cultural heritage. This application can adjust the display content of the system according to the historical data and behavioral preferences of user operations, and provide a tour path that better meets user needs. At the same time, the system can dynamically update the virtual data of cultural heritage, so that users can always obtain the latest cultural heritage information. This flexible feedback mechanism can effectively improve user satisfaction and experience, and has obvious advantages over traditional static virtual tour methods. This application achieves highly accurate digitization of cultural heritage through 3D scanning and virtual data construction of cultural heritage; through augmented reality interactive models and virtual tour data generation, it provides users with an immersive, personalized and interactive virtual cultural heritage experience. Compared with existing virtual tour technologies, this application solves problems such as insufficient display accuracy, insufficient interactivity, and poor personalization, significantly improves the digital communication effect of cultural heritage, and provides new technical paths and application scenarios for the protection and inheritance of cultural heritage.

[0027] In some examples, inputting the cultural heritage virtual data and the user operation data into an augmented reality interaction model to generate virtual tour data includes: Mapping the cultural heritage data in the virtual space according to the user's current location information to extract the cultural heritage data within a preset distance of the user's current location; Adjusting the virtual tour content based on the user's interactive operation, wherein the interactive operation includes hand operation and perspective rotation operation; The virtual tour data is generated according to the adjusted virtual tour content and the data of interest.

[0028] For example, during a virtual tour, the system will first locate the user's position in the virtual space based on the user's current location information. The user's location information can be obtained through the GNSS, sensors, or positioning systems in VR / AR devices and other XR devices of the user's device. These data will help the system determine the user's position and movement trajectory in the virtual tour.

[0029] The core of mapping cultural heritage data into virtual space is to map the user's location information in the physical world with the cultural heritage data in the virtual space. The cultural heritage data in the virtual space is generated based on the 3D scanning data of cultural heritage in the real world. Therefore, when the user moves, the system will automatically load and display the virtual data of cultural heritage near the user's current location in the virtual space according to his actual location.

[0030] Extract cultural heritage data within a preset distance of the user's current location. The system will extract cultural heritage data within the preset distance range of the user's current location. For example, when a user approaches a historical building in the virtual space, the system will extract and load the cultural heritage data of the building and its surroundings for the user to further explore and interact with. This design ensures that the user's virtual tour experience is dynamic and closely related to their actual actions and points of interest.

[0031] For example, when a user is touring a virtual museum, the system will automatically load the virtual data of the exhibits in the current exhibition area based on the user's location information, and display the exhibits that the user may see next based on the user's movement direction. If the user approaches an exhibit, the system will extract the virtual data of the exhibit and present detailed information on the user's display device.

[0032] In order to enhance the user's interactivity in the virtual tour, this application can adjust the virtual tour content through a variety of interactive operations. The user's operations include but are not limited to the following: Hand operation: Users can interact with virtual cultural heritage data through manual operations such as touch screen, gesture control, and click. For example, users can click on a cultural heritage object to view its detailed information, or zoom in or out of the virtual scene through sliding gestures. This operation can help users explore cultural heritage details more intuitively.

[0033] Perspective rotation operation: Users can change the tour direction by moving their heads (when using AR / VR devices or other XR devices) or adjusting the perspective through the device. The system will dynamically adjust the displayed virtual tour content according to the user's perspective change. For example, when the user turns his head, the system will display the virtual cultural heritage part in his current field of view, ensuring the immersive and realistic tour experience.

[0034] These interactive operations are an important part of the augmented reality interaction model. Every interaction of the user will trigger the system to adjust the virtual tour content to adapt to the user's operational needs. In this way, users can freely explore the cultural heritage in the virtual environment and get a personalized tour experience. For example, when a user walks in front of an ancient building in a virtual tour, he can zoom in to see the fine carvings of the building through gestures, or rotate the view to see the whole picture of the building. When a user clicks on a mural on a wall, the system will display the historical background and detailed description of the mural.

[0035] When the user adjusts the virtual tour content through interactive operations, the system will generate virtual tour data based on the user's behavior and points of interest. The process of generating virtual tour data includes the following steps: Analyze adjusted virtual tour content: The system analyzes the user's adjusted tour trajectory and operation behavior to determine the user's focus and cultural heritage content that they are interested in. For example, if a user zooms in on a cultural relic several times during a virtual tour or stays in that area for a long time, the system will consider that the user is particularly interested in that part of the content.

[0036] Extraction of data of interest: The system will extract content related to the user's interest from the virtual cultural heritage data. This content may include detailed historical background, audio commentary, relevant pictures, documentary records and other information to help users gain a deeper understanding of cultural heritage.

[0037] Generate virtual tour data: Based on the user's behavior and data of interest, the system generates corresponding virtual tour data to enrich the user's tour experience. This data may include automatically played tour voice, display of relevant background information, recommended tour routes, etc. In this way, the system can not only provide users with basic tour information, but also make personalized recommendations based on the user's operating habits and interests.

[0038] For example: When a user shows special interest in an exhibit in a virtual exhibition, such as viewing the exhibit details multiple times or staying near the exhibit for a long time, the system will automatically generate detailed guide information about the exhibit, including its historical background, cultural significance, and related audio guides, and even recommend other exhibition areas or exhibits related to the exhibit.

[0039] The method proposed in the embodiment of the present application maps the user's actual location information with the cultural heritage data in the virtual space, extracts the virtual data of the cultural heritage near the current location, and ensures that the user can dynamically browse the content related to his location. Through hand operation and perspective rotation operation, the user can interact with the virtual cultural heritage and adjust the virtual tour content. This highly interactive design allows users to freely explore cultural heritage and gain in-depth understanding based on points of interest. The system generates personalized virtual guide data based on the user's operating habits and points of interest, so that users can obtain a richer and more targeted guide experience during the tour. This virtual tour solution not only enhances the user's interactivity and personalized experience, but also improves the digital dissemination effect of cultural heritage through immersive guidance and dynamic data generation, so that cultural heritage can be better inherited and displayed in a virtual environment.

[0040] In some examples, this also includes: Classifying the cultural heritage virtual data based on cultural type information through adaptive resonance theory to obtain multiple categories of cultural heritage sub-virtual data, wherein the cultural heritage sub-virtual data includes historical building virtual data, historical musical instrument virtual data and mural virtual data; Sending all the cultural heritage sub-virtual data to the client of the corresponding cultural category research institution, so that the corresponding cultural category research institution performs cultural research operations and generates heritage extension research data; Sending all the cultural heritage sub-virtual data to the online forum community of the corresponding cultural category, so that the online forum community of the corresponding cultural category can discuss and perform secondary creation operations, and generate heritage extension creation data; All of the cultural heritage sub-virtual data are sent to the intelligent generation model of the corresponding cultural category, so that the intelligent generation model of the corresponding cultural category performs a recommended video generation operation and generates heritage extension recommendation data.

[0041] For example, firstly, the cultural heritage virtual data is classified by Adaptive Resonance Theory (ART). ART is a classification method based on neural networks, which is good at processing dynamic input data and classification tasks, and can receive new information without losing old data. Using ART, the cultural heritage virtual data can be automatically classified by type.

[0042] Cultural heritage usually involves multiple categories of objects, including historical buildings, musical instruments, murals, etc. Each type of cultural heritage is different in attributes, structure and information display. Cultural type information refers to the labels or characteristic information used to distinguish different types of cultural heritage.

[0043] ART analyzes cultural type information and reasonably divides cultural heritage virtual data to generate multiple categories of cultural heritage sub-virtual data, such as historical building virtual data, historical musical instrument virtual data, and mural virtual data. The purpose of this classification is to ensure that each type of cultural heritage can be independently stored, studied, and displayed according to its characteristics.

[0044] For example, in a virtual data set of cultural heritage, ART can classify them into corresponding historical buildings, musical instruments or murals according to the three-dimensional features of the building structure, the shape and texture features of the musical instruments, and the color and composition features of the murals, to facilitate subsequent targeted research and operations.

[0045] After the classification is completed, the solution sends all the cultural heritage sub-virtual data to the clients of the research institutions of the corresponding cultural categories. These research institutions can conduct in-depth research on different types of cultural heritage data according to their own professional fields. Each research institution can carry out a series of research operations based on the received cultural heritage sub-virtual data. For example, historical architecture research institutions can analyze the structure and evolution of ancient buildings through virtual data, historical instrument researchers can conduct acoustic research on virtual instruments, and mural researchers can study painting techniques and color preservation issues based on digital data. Through research operations, research institutions will generate heritage extended research data, which contains deeper cultural analysis and research results. These extended research data can not only help further enrich the digital information of cultural heritage, but also provide a scientific basis for the preservation, restoration and dissemination of cultural heritage.

[0046] This method also includes sending the cultural heritage sub-virtual data to the online forum community of the corresponding cultural category. These communities gather enthusiasts, creators and researchers who love cultural heritage, and they can discuss and create secondary works based on virtual data. In the online forum community, users can discuss around the cultural heritage virtual data and share their understanding and ideas about cultural heritage. At the same time, users can also perform secondary creations based on these data, such as making illustrations, models, short videos, etc. related to virtual heritage, thereby stimulating the public's attention and interest in cultural heritage. The discussions and creations of users in the community will generate heritage extension creation data, which usually include virtual works created by users and related discussion records. These creations not only enrich the way cultural heritage is disseminated, but also give new artistic vitality to cultural heritage. For example: in a community of historical instrument enthusiasts, users have heated discussions based on virtual instrument data, share the application of the instrument in different musical styles, and make virtual performance videos of the instrument based on the virtual instrument data, which become part of the heritage extension creation data.

[0047] Finally, the present application also includes sending the cultural heritage sub-virtual data to the intelligent generation model of the corresponding cultural category. The intelligent generation model is an automatic content generation technology based on artificial intelligence, which can generate multimedia information such as recommended videos and guided tour content based on the input virtual data. The intelligent generation model will automatically generate recommended videos related to the data based on the received cultural heritage sub-virtual data. These videos usually include historical introductions, virtual displays, and interactive explanations of cultural heritage. The intelligent generation model can combine the characteristics of cultural categories to generate customized recommended videos for different cultural heritages. These automatically generated recommended videos and related content will be provided to users as heritage extension recommendation data. Recommended videos can not only be displayed on virtual tour platforms, but also widely disseminated through channels such as social media and educational platforms to help spread and promote cultural heritage. For example: for mural virtual data, the intelligent generation model can generate a recommended video showing the historical background of the mural, the story of the characters in the painting, and the restoration process of the mural, and promote these videos as heritage extension recommendation data to online platforms related to cultural heritage.

[0048] In some examples, enabling the corresponding cultural category research institution to perform cultural research operations and generate heritage extension research data includes: Obtain information on the characteristics of the cultural knowledge base of research institutions; Extracting cultural element information of the cultural heritage sub-virtual data using natural language processing and entity recognition methods; Constructing a related knowledge graph based on the cultural knowledge base feature information and the cultural element information; Generate basic extended data through the TransE / TransH reasoning algorithm according to the associated knowledge graph; The heritage extended research data is generated based on rule reasoning according to the basic extended data to update the cultural knowledge base of the research institution.

[0049] For example, the characteristic information of the cultural knowledge base of the research institution is obtained, that is, the knowledge data related to a specific cultural category currently owned by the research institution. Such data may include existing cultural heritage research results, historical documents, archaeological records, cultural heritage restoration information, etc.

[0050] The characteristic information of cultural knowledge base can be presented through structured data (such as tables in databases) or unstructured data (such as document text). This information provides the research institution with background knowledge of a certain cultural category and is the basis for subsequent data processing and reasoning.

[0051] Using Natural Language Processing (NLP) and Named Entity Recognition (NER) technology, cultural element information is extracted from the cultural heritage sub-virtual data. These element information refers to the core information units related to cultural heritage, such as the name of the historical building, the construction time, the architectural style, the type of musical instrument, the timbre characteristics, and the images and characters in the murals.

[0052] Natural language processing converts cultural heritage description text into processable data structures through word segmentation, syntactic analysis and other methods. Entity recognition uses the NER algorithm in NLP to identify important cultural elements in the description. For example, from "The building is of Tang Dynasty style and was built in 850 AD", key entities such as "Tang Dynasty" and "850 AD" are identified.

[0053] Then, based on the extracted cultural element information and the characteristic information of the cultural knowledge base of the research institution, a related knowledge graph is constructed. Knowledge graph is a method of representing knowledge with a graph structure, where each node represents an entity and each edge represents the relationship between entities.

[0054] The existing knowledge nodes in the feature information of the cultural knowledge base are associated with the new cultural element nodes extracted from the cultural heritage sub-virtual data. For example, if the knowledge base already has information on "Tang Dynasty architecture", the extracted "Tang Dynasty architecture" element will be connected to the existing nodes in the knowledge base by building a relationship (such as "belongs to").

[0055] The formula can be expressed as: ; in, It is the knowledge graph constructed. represents the head entity in the knowledge graph, represents the tail entity in the knowledge graph, yes and The relationship between the head entity and the tail entity, is the entity set in the knowledge base, It is a set of cultural elements. is a relationship set.

[0056] Once the knowledge graph is built, reasoning algorithms (such as TransE or TransH) are used to generate basic extended data. These algorithms are embedded models that map entities and relationships in the knowledge graph into a low-dimensional vector space, so that reasoning can be performed through geometric operations.

[0057] The basic idea of ​​the TransE (Translation Embedding) / TransH (Translation Embedding on Hyperplanes) inference algorithm is to transform the triples ( , , ) are embedded into the vector space and are expected to satisfy the following formula: ; in, represents the head entity in the knowledge graph, represents the tail entity in the knowledge graph, yes and The relationship between the head entity and the tail entity. This formula can be used to derive new relationships or verify the correctness of existing relationships.

[0058] TransE assumes that all relations are flat, while TransH can handle complex multiple relations and allows entities to have different embedding vectors in different relations. Therefore, TransH is more suitable for handling complex cultural heritage knowledge reasoning.

[0059] The formula is: ; in, represents the head entity in the knowledge graph, represents the tail entity in the knowledge graph, yes and The relationship between the head entity and the tail entity, Indicates possible errors in the reasoning process. By calculating new relationships, basic extended data can be generated.

[0060] Finally, rule-based reasoning methods are used to generate heritage extended research data. Rule-based reasoning refers to the use of predefined rule sets to perform higher-level reasoning based on basic extended data to draw new conclusions. These conclusions will further expand the existing knowledge base and provide valuable new information for research. Rule-based reasoning is usually based on logical rules, such as "if a building belongs to the Tang Dynasty and has certain structural features, it is inferred that it belongs to a certain architectural school." Through these rules, new conclusions can be inferred from the basic extended data to generate extended research data.

[0061] The formula can be expressed as: ; in, is the Heritage Extension Research Data, It is a rule-based reasoning method. It is the basic extended data generated by TransE / TransH.

[0062] The generated heritage extension research data can be further used to update the cultural knowledge base of research institutions, and update the latest research results, reasoning results and data into the knowledge base to form a dynamically updated knowledge system. With each research, the knowledge base will be continuously expanded and optimized, providing richer resources for subsequent cultural research.

[0063] The formula is: ; in, It is an updated cultural knowledge base. is the entity set in the knowledge base, It is the heritage extension research data.

[0064] The embodiments of the present application provide background support for research by acquiring characteristic information of the cultural knowledge base. Extract cultural element information and obtain core cultural information from virtual data through NLP and entity recognition technology. Construct an associated knowledge graph to establish connections between new cultural elements and existing knowledge base information. Generate basic extended data based on vector space reasoning by using the TransE / TransH reasoning algorithm. Generate heritage extension research data based on rule reasoning and update the cultural knowledge base of the research institution. The method proposed in the embodiments of the present application can not only realize the automatic classification and reasoning of cultural heritage data, but also improve the efficiency and depth of cultural research by dynamically updating the knowledge base.

[0065] In some examples, enabling the online forum community of the corresponding cultural category to conduct discussions and secondary creation operations and generate heritage extension creation data includes: Acquire the uploaded information of the online community user, wherein the uploaded information includes text description information, sketch information and initial creative material information; Based on the uploaded information and the cultural heritage sub-virtual data, a generative adversarial network model is used to perform a preset number of training and optimization operations to generate heritage extension creation data.

[0066] For example, users in the online forum community can upload a variety of creation-related materials, which will serve as the basis for generating heritage extension creation data. The information uploaded by users mainly includes the following categories: Text description information: It is the user's creative description of a cultural heritage, such as the architectural style, historical background, or artistic form. This type of information is mainly uploaded in the form of natural language.

[0067] Sketch information: Sketches or designs drawn for users, which may be transformations or creative reproductions of cultural heritage.

[0068] Initial creative material information: basic materials uploaded by users during creation, including pictures, sounds, videos, etc. These materials can be combined with cultural heritage sub-virtual data to generate new creative works.

[0069] The information uploaded by the user can be expressed by the formula: ; in, Represents the user's uploaded information collection, Represents text description information. Indicates sketch information. Indicates the initial creative material information.

[0070] The creation information uploaded by users is combined with the cultural heritage sub-virtual data. The cultural heritage sub-virtual data is generated through the previous adaptive resonance theory (ART) classification and contains different categories of cultural heritage virtual model data, such as historical buildings, historical musical instruments or murals.

[0071] The purpose of this step is to integrate the user's creative information with cultural heritage data, so that secondary creation can be expanded and innovated while maintaining the original characteristics of cultural heritage.

[0072] The formula is: ; in, Represents a collection of cultural heritage sub-virtual data, representing different types of cultural heritage sub-virtual data, such as historical building virtual data , Historical instrument virtual data and mural virtual data .

[0073] Generative Adversarial Network (GAN) is a framework consisting of two neural networks: Generator and Discriminator. In this scheme, GAN is used to generate heritage extension creation data.

[0074] Generator: The Generator receives user uploaded information and cultural heritage sub-virtual data, and attempts to generate new cultural heritage creation data (such as new virtual models or artistic creations) based on these inputs.

[0075] Discriminator: The task of the discriminator is to distinguish between the creative data generated by the generator and the real cultural heritage sub-virtual data, and to determine whether the generated data is realistic.

[0076] The training process of GAN is a game process between the generator and the discriminator. The generator tries to "cheat" the discriminator and generate creative data that is as realistic as possible, while the discriminator continuously improves its ability to identify false data. After multiple training and optimization, the generator will be able to generate high-quality extended creative data.

[0077] The training process of GAN is expressed as follows: ; in, Representation Generator The optimization goal of the generator The optimization goal is to minimize the discriminator The generator generates fake data based on the input The ability to discern, Representation Discriminator The optimization goal of the discriminator The optimization goal is to maximize its own discrimination ability. represents a generator, represents the discriminator, represents the distribution of real cultural heritage sub-virtual data, represents the distribution of random noise input to the generator, is the random noise input to the generator, is the fake data generated by the generator based on the input, It is the virtual data of real cultural heritage. is the judgment of the discriminator on the real cultural heritage sub-virtual data, Represents sampling from the distribution of real cultural heritage sub-virtual data The mathematical expectation of Represents sampling from the distribution of random noise input to the generator The mathematical expectation of Representation Discriminator Virtual data of real cultural heritage The logarithm of the output probability, express With the discriminator The generator generates fake data based on the input The logarithm of the difference in the output probabilities.

[0078] The generator and discriminator are continuously optimized in a preset number of training cycles. Each time the generator tries to generate more realistic heritage creation data, the discriminator adjusts its ability to identify fake data, until the generator can successfully generate extended creation data with creative and cultural elements.

[0079] Preset number of training times: The proposal mentions that the training and optimization operations are “preset times”, which means that GAN will be optimized multiple times within the set training cycle until the generator’s generation capacity is strong enough to generate extended creative data that meets the characteristics of cultural heritage.

[0080] After GAN training is completed, the generator will generate heritage extension creation data that conforms to the characteristics of cultural heritage. These data are the combination of user uploaded information and cultural heritage sub-virtual data, which can show innovation and artistry while retaining the core elements of cultural heritage. The generated heritage extension creation data can include: new virtual building models, innovative sound effects or designs of virtual musical instruments, and the re-creation or re-design of murals, that is: ; in, Represents the generated legacy extended creation data, represents a generator, It is a collection of user's uploaded information. It is a collection of cultural heritage sub-virtual data, which respectively represent different types of cultural heritage sub-virtual data.

[0081] The embodiments of the present application combine the generation capability of the GAN model and the richness of cultural heritage by enabling users to create secondary works in the online community of cultural heritage and ultimately generating heritage extension creation data, thereby promoting cultural inheritance and giving users the freedom to create and the opportunity to innovate.

[0082] In some examples, the step of causing the intelligent generation model of the corresponding cultural category to perform a recommended video generation operation and generate heritage extension recommendation data includes: Get the hot tag information corresponding to the current hot video information; Get current holiday information; Calculate the correlation information of each type of cultural heritage sub-virtual data according to the hot tag information and the current holiday information; Determine the cultural heritage sub-virtual data whose correlation information is greater than a preset correlation as the creation source data; The creation source data, the hot tag information and the current holiday information are input into a target Transformer model to generate the heritage extension recommendation data.

[0083] For example, the system needs to obtain popular video content on the current network and extract hot tag information related to these videos. Hot tag information refers to keywords or topic tags related to the current popular videos (such as "historical buildings", "Chinese style music", "Spring Festival culture", etc.), which can reflect the current user's hot interests.

[0084] Hot tag information can be obtained by analyzing metadata, video titles, descriptions, or user comments of popular videos. For example, if videos about ancient architecture are popular recently, the tag information may include "architecture", "history", "cultural heritage", etc.

[0085] When generating recommended videos, the system also needs to take into account current holiday information, as holidays may affect user interests. For example, during the Spring Festival, users may pay more attention to content related to traditional festival culture.

[0086] Current holiday information: The system can obtain current holiday information from the calendar, which may include holiday names, times, and related cultural backgrounds. For example, if it is the Spring Festival, the holiday information will include "Spring Festival", "Lunar New Year", etc.

[0087] Next, by calculating the correlation between hot tag information, current holiday information and various types of cultural heritage sub-virtual data, the video creation materials suitable for the current scene are screened. The correlation calculation can be based on indicators such as tag matching, semantic similarity or historical click-through rate.

[0088] Relevance information of cultural heritage sub-virtual data: The relevance information of cultural heritage sub-virtual data refers to the matching degree between hot tag information and current holiday information and cultural heritage sub-virtual data. For example, if the current holiday is "Mid-Autumn Festival", the materials related to Mid-Autumn Festival culture (such as Mid-Autumn Festival customs, traditional musical instruments, etc.) in the cultural heritage sub-virtual data will have a high relevance.

[0089] The formula is: ; in, Indicates the degree of association, Represents a collection of cultural heritage sub-virtual data, representing different types of cultural heritage sub-virtual data. Indicates semantic similarity, and is the weight parameter of the hotspot tag information and the current holiday information. Indicates hotspot tag information. Indicates the current holiday information. Represents a collection of cultural heritage sub-virtual data Information about hot tags The semantic similarity between and to measure their relevance. Represents a collection of cultural heritage sub-virtual data Information about current holidays The semantic similarity between . This function calculates and The similarity is used to evaluate the degree of association between them.

[0090] Once the relevance information of the cultural heritage sub-virtual data is calculated, the solution determines the cultural heritage sub-virtual data with a relevance greater than a preset threshold as the creative source data. These creative source data are the basic materials for finally generating the recommended video.

[0091] The creative source data is the cultural heritage sub-virtual data that is highly related to current hot spots and holidays. For example, if the hot tag information is "Spring Festival" and the current holiday information is also "Spring Festival", the cultural heritage materials related to the Spring Festival (such as Spring Festival customs, dragon dance performances, etc.) will be selected as the creative source data.

[0092] ; in, Represents the creative source data, It is the first in the set of cultural heritage sub-virtual data. elements, is the preset correlation threshold. , They are hot tag information and current holiday information. Indicates the degree of association.

[0093] Finally, the selected creative source data, hot tag information, and current holiday information are input into a target Transformer model to generate heritage extension recommendation data. The Transformer model is a powerful natural language processing and generation model that can generate high-quality text or video recommendation data based on the input data. The Transformer model processes the input creative source data, hot tag information, and current holiday information using a multi-head attention mechanism. The Transformer model can generate recommended video scripts, subtitles, or video structures that are relevant to user needs.

[0094] The calculation process of the Transformer model can be expressed as: ; in, Represents legacy extension recommendation data, is the target model used to generate recommendations, , , They are creation source data, hot tag information and current holiday information.

[0095] The embodiment of the present application generates cultural heritage recommendation videos that meet the needs of hot videos and holidays, and generates heritage extension recommendation data. This recommendation video generation mechanism based on hot spots and festivals not only ensures the combination of cultural heritage promotion and current popular trends, but also enhances the dissemination effect of cultural heritage at specific time points.

[0096] In some examples, this also includes: Performing intelligent evaluation on the heritage extension creation data and the heritage extension recommendation data to obtain an evaluation result; The heritage extension creation data and the heritage extension recommendation data whose evaluation results are greater than a preset result level are sent to an interactive terminal of a corresponding cultural tourist area.

[0097] Exemplarily, after generating heritage extension creation data (such as users' secondary creations) and heritage extension recommendation data (such as intelligently generated video content), the system first scores or rates these data through an intelligent evaluation model to determine whether their quality meets the expected standards.

[0098] Intelligent evaluation models can provide comprehensive scores based on multiple indicators, which may include content quality, innovation, relevance to cultural heritage, user interaction feedback, etc. Intelligent evaluation models may use machine learning models (such as evaluation models based on neural networks) to automatically analyze these data, score and generate evaluation results.

[0099] The formula is: ; in, is the evaluation score corresponding to the evaluation result, Represents legacy extended creation data, Represents legacy extension recommendation data, Represents an intelligent evaluation model, which is used to analyze input data and return an evaluation score.

[0100] After scoring each data through the intelligent evaluation model, the system will obtain a specific first evaluation result, which indicates the overall quality level of the data. The first evaluation result can be a numerical score or a grade, such as a score from 1 to 10 or a grade division such as A, B, C, etc.

[0101] The first evaluation result can be obtained by weighted average of different quality indicators, for example: ; in, This is the first evaluation result. Represents the content quality score. represents the innovation score, represents the relevance score to cultural heritage, Represents the user interaction feedback score, , , , are the weights of different indicators.

[0102] Next, the system compares all the Heritage Extension Creation Data and Heritage Extension Recommendation Data with the preset evaluation level to filter out high-quality data. The evaluation results of these data must be greater than or equal to a preset result level to be selected. The preset result level is a minimum standard for the evaluation results. Only data with a score higher than or equal to this level will be further processed. The preset level can be set by the system administrator or based on user feedback.

[0103] The filtering condition can be expressed by the formula: ; in, Represents the selected data set. is the evaluation score corresponding to the evaluation result, Indicates heritage extension creation data or heritage extension recommendation data, Indicates the preset evaluation level threshold.

[0104] Once high-quality heritage extension creation data and heritage extension recommendation data are screened, the system sends these data to interactive terminals in specific cultural tour areas. These terminals may be touch screen devices, AR / VR experience devices, etc. in museums, historical sites or other cultural experience areas, through which users can directly interact with the data. These terminal devices provide users with a direct interactive experience with cultural heritage. Users can watch recommended videos, view creatively reproduced heritage content, and even perform more interactive operations with cultural data (such as virtual tours, AR experiences, etc.) through these terminals.

[0105] This method realizes the intelligent screening and publishing of heritage extension creation data and heritage extension recommendation data. This mechanism ensures the quality of creation and recommendation content released to users through intelligent evaluation and screening process, improves users' cultural experience, and promotes the effective dissemination of cultural heritage.

[0106] In some examples, the intelligently evaluating the legacy extension creation data and the legacy extension recommendation data to obtain an evaluation result includes: Determine an evaluation result of the extended creation based on the artistic score, historical consistency score and creativity score of the heritage extended creation data; Determine an extension recommendation evaluation result based on the relevance score, user feedback score and audience coverage score of the heritage extension recommendation data; The evaluation result is determined based on the extension creation evaluation result and the extension recommendation evaluation result.

[0107] For example, first, the system needs to evaluate the heritage extension creation data. Heritage extension creation data is usually generated by users in the secondary creation process, including artistic reproduction and innovative adaptation of cultural heritage. In order to ensure the quality of these creation data, the evaluation is based on the following three core scoring dimensions: Artistic Score: Evaluates the artistic level of the creation, including visual effects, uniqueness of expression, creativity, etc.

[0108] Historical Consistency Score: Assess whether the creation is consistent with the historical facts of the original cultural heritage to avoid inaccurate or distorted cultural representation.

[0109] Creativity Score: Assess the degree of innovation of the creation and encourage artistic innovation and unique interpretation based on cultural heritage.

[0110] Based on these three scores, the evaluation results of the extended creation can be determined, and the final score can be generated by weighted average. The formula is: ; in, is the evaluation result corresponding to the extended creation data, It's an artistic rating. is the historical consistency score, is the creativity score, , , is the weight of each scoring dimension.

[0111] For heritage extension recommendation data, the system uses different evaluation criteria. These extension recommendation data are usually recommended videos or content for cultural heritage. The evaluation goal is to ensure its relevance, good user feedback, and wide audience coverage. The evaluation is based on the following three scoring dimensions: Relevance Score: Evaluates the relevance of recommended content to user needs or current hot topics to ensure that the recommended content is in line with the user's interests.

[0112] User Feedback Score: Based on users’ evaluation of the recommended content, such as likes, comments, and shares, it reflects the popularity of the recommended content.

[0113] Audience Coverage Score: Evaluates the coverage of recommended content among the audience, reflecting the content’s dissemination scope and audience acceptance.

[0114] Similarly, based on these three scores, the system can calculate the extended recommendation evaluation results, the formula is: ; in, is the evaluation result corresponding to the extended recommendation data, is the relevance score, is the user feedback rating, is the audience reach score, , , are the weights of different indicators.

[0115] Finally, the system evaluates the corresponding evaluation results of the extended creation data ( ) and the evaluation results corresponding to the extended recommendation data ( ) Comprehensively calculate the second evaluation result ( ). This step is to unify the scoring results of the creation data and the recommendation data, so as to finally decide which data can be published to the interactive terminals in the cultural tourism area.

[0116] The second evaluation result can be obtained by weighted synthesis, the formula is: ; in, This is the second evaluation result. is the evaluation result corresponding to the extended creation data, is the evaluation result corresponding to the extended recommendation data, and It is the weight used for comprehensive evaluation.

[0117] Suppose there is a user's secondary creation data, including a re-creation of an ancient building. The system uses intelligent evaluation to score its artistry, historical consistency, and creativity. For example: Artistry score: 8.5; Historical consistency score: 7.0; Creativity score: 9.0; : 0.4; : 0.3; : 0.3.

[0118] Calculate the evaluation results corresponding to the extended creation data: ; Another recommended video data is scored based on relevance, user feedback and audience coverage. For example: relevance score: 9.0; user feedback score: 8.0; audience coverage score: 7.5; : 0.5; : 0.3; : 0.2.

[0119] Calculate the evaluation results corresponding to the extended recommendation data: ; The system calculates the second evaluation result based on the evaluation result corresponding to the extended creation data and the evaluation result corresponding to the extended recommendation data. For example: : 0.6; :0.4.

[0120] The second evaluation result is: ; Through the above steps, the system can conduct multi-dimensional analysis of heritage extension creation data and extension recommendation data based on intelligent evaluation to generate the second evaluation result. This evaluation result ensures the high quality of cultural content and provides a scientific basis for the final data release decision.

[0121] In some examples, the specific steps of determining the interactive terminal corresponding to the cultural tourist area include: Obtain user location information, cultural heritage area map data, interactive terminal location data, user preference data, and user preferred interaction method data; The interactive terminal corresponding to the cultural sightseeing area is determined based on the user location information, the cultural heritage area map data, the interactive terminal location data, the user preference data and the user preferred interaction mode data.

[0122] Exemplarily, after obtaining all necessary information, the system needs to perform comprehensive calculations and analyses based on user location information, cultural heritage area map data, interactive terminal location data, user preference data, and user preferred interaction method data to determine the most suitable interactive terminal for the user.

[0123] The system first determines the interactive terminals near the user based on the user's location information. Using the cultural heritage area map data and the interactive terminal location data, the system can calculate the distance between the user and each interactive terminal. Then, the system matches the user's preference data with the cultural content provided by the interactive terminal and selects the terminal that provides the content that the user is interested in. Finally, the system matches the user's preferred interaction method data with the interaction methods supported by the interactive terminal and selects the interactive terminal corresponding to the cultural tourist area.

[0124] The formula is: ; in, Indicates to select a Make the objective function in the brackets reach the minimum value, It represents the optimal candidate interactive terminal, that is, it selects the best terminal that can meet the user's location, content preference and interaction method preference. Represents candidate interactive terminals, and the system selects the best terminal from these candidate interactive terminals. Indicates the user's current location and candidate interactive terminal locations This distance measures the physical proximity between the user and each candidate interaction terminal. Indicates candidate interactive terminals Provide cultural content. Indicates candidate interactive terminals Supported interaction methods, such as touch, voice control, etc. Indicates candidate interactive terminals Cultural content provided and user content preferences The semantic similarity between them is used to determine whether the candidate interactive terminal content meets the user's interests. Indicates candidate interactive terminals Supported interaction methods Interact with user preferences The semantic similarity between them is used to evaluate whether the interaction mode of the candidate interactive terminal meets the user's preference. is a weight parameter used to adjust the influence of content preference matching. A higher value indicates that content matching is more important for selecting a terminal. is another weight parameter used to adjust the influence of interaction mode matching. A value of indicates that the interaction mode matching is more important for selecting candidate interaction terminals.

[0125] See also Figure 2 , a new media cultural heritage interactive communication system based on digital twins provided in an embodiment of the present application, comprising: A first generating unit 21 is used to construct a model based on the 3D scanning data of the cultural heritage based on the virtual heritage to generate virtual data of the cultural heritage; The second generating unit 22 inputs the cultural heritage virtual data and the user operation data into the augmented reality interaction model to generate virtual tour data, wherein the virtual tour data includes the cultural heritage virtual data and the virtual tour guide data corresponding to the target user's tour location; The interactive control unit 23 is used to send the virtual tour data to the experience terminal corresponding to the target user, so that the target user can perform a virtual tour.

[0126] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0127] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0128] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0129] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0130] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0131] An embodiment of the present application also provides a computer program product, which includes computer software instructions. When the computer software instructions are executed on a processing device, the processing device executes the process of interactive dissemination of new media cultural heritage based on digital twins in the corresponding embodiment.

[0132] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on the computer, the process or function according to the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from a website site, a computer, a server, or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (Digital Subscriber Line, DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server, or data center. The computer-readable storage medium may be any available medium that a computer can store or a data storage device such as a server or a data center that includes one or more available media integrated. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)), etc.

[0133] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0134] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0135] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0136] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0137] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc., various media that can store program codes.

[0138] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A new media cultural heritage interactive communication method based on digital twins, characterized in that: include: Use the 3D scanning data of cultural heritage to build a model based on virtual heritage to generate virtual data of cultural heritage; Inputting the cultural heritage virtual data and the user operation data into the augmented reality interaction model to generate virtual tour data, wherein the virtual tour data includes the cultural heritage virtual data and the virtual tour guide data corresponding to the target user's tour location; The virtual tour data is sent to an experience terminal corresponding to a target user, so that the target user can conduct a virtual tour.

2. The new media cultural heritage interactive communication method based on digital twin according to claim 1 is characterized in that: The step of inputting the cultural heritage virtual data and the user operation data into the augmented reality interaction model to generate virtual tour data includes: Mapping the cultural heritage data in the virtual space according to the user's current location information to extract the cultural heritage data within a preset distance of the user's current location; Adjusting the virtual tour content based on the user's interactive operation, wherein the interactive operation includes hand operation and perspective rotation operation; The virtual tour data is generated according to the adjusted virtual tour content and the data of interest.

3. The new media cultural heritage interactive communication method based on digital twin according to claim 1 is characterized in that: Also includes: Classifying the cultural heritage virtual data based on cultural type information through adaptive resonance theory to obtain multiple categories of cultural heritage sub-virtual data, wherein the cultural heritage sub-virtual data includes historical building virtual data, historical musical instrument virtual data and mural virtual data; Sending all of the cultural heritage sub-virtual data to the client of the corresponding cultural category research institution, so that the corresponding cultural category research institution performs cultural research operations and generates heritage extension research data; Sending all the cultural heritage sub-virtual data to the online forum community of the corresponding cultural category, so that the online forum community of the corresponding cultural category can discuss and perform secondary creation operations, and generate heritage extension creation data; All of the cultural heritage sub-virtual data are sent to the intelligent generation model of the corresponding cultural category, so that the intelligent generation model of the corresponding cultural category performs a recommended video generation operation and generates heritage extension recommendation data.

4. The new media cultural heritage interactive communication method based on digital twin according to claim 3 is characterized in that: The method enables the corresponding cultural research institutions to conduct cultural research operations and generate heritage extension research data, including: Obtain information on the characteristics of the cultural knowledge base of research institutions; Extracting cultural element information of the cultural heritage sub-virtual data using natural language processing and entity recognition methods; Constructing a related knowledge graph based on the cultural knowledge base feature information and the cultural element information; Generate basic extended data through the TransE / TransH reasoning algorithm according to the associated knowledge graph; The heritage extended research data is generated based on rule reasoning according to the basic extended data to update the cultural knowledge base of the research institution.

5. The new media cultural heritage interactive communication method based on digital twin according to claim 3 is characterized in that: The method enables the online forum community of the corresponding cultural category to conduct discussions and secondary creation operations, and generate heritage extension creation data, including: Acquire the uploaded information of the online community user, wherein the uploaded information includes text description information, sketch information and initial creative material information; Based on the uploaded information and the cultural heritage sub-virtual data, a generative adversarial network model is used to perform a preset number of training and optimization operations to generate heritage extension creation data.

6. The new media cultural heritage interactive communication method based on digital twin according to claim 3 is characterized in that: The method of causing the intelligent generation model of the corresponding cultural category to perform a recommended video generation operation and generate heritage extension recommendation data includes: Get the hot tag information corresponding to the current hot video information; Get current holiday information; Calculate the correlation information of each type of cultural heritage sub-virtual data according to the hot tag information and the current holiday information; Determine the cultural heritage sub-virtual data whose correlation information is greater than a preset correlation as the creation source data; The creation source data, the hot tag information and the current holiday information are input into a target Transformer model to generate the heritage extension recommendation data.

7. The new media cultural heritage interactive communication method based on digital twin according to claim 3 is characterized in that: Also includes: Performing intelligent evaluation on the heritage extension creation data and the heritage extension recommendation data to obtain an evaluation result; The heritage extension creation data and the heritage extension recommendation data whose evaluation results are greater than a preset result level are sent to an interactive terminal of a corresponding cultural tourist area.

8. The new media cultural heritage interactive communication method based on digital twin according to claim 7 is characterized in that: The intelligently evaluating the heritage extension creation data and the heritage extension recommendation data to obtain an evaluation result includes: Determine an evaluation result of the extended creation based on the artistic score, historical consistency score and creativity score of the heritage extended creation data; Determine an extension recommendation evaluation result based on the relevance score, user feedback score and audience coverage score of the heritage extension recommendation data; The evaluation result is determined based on the extension creation evaluation result and the extension recommendation evaluation result.

9. The new media cultural heritage interactive communication method based on digital twin according to claim 7 is characterized in that: The specific steps of determining the interactive terminal corresponding to the cultural tourist area include: Obtain user location information, cultural heritage area map data, interactive terminal location data, user preference data, and user preferred interaction method data; The interactive terminal corresponding to the cultural sightseeing area is determined based on the user location information, the cultural heritage area map data, the interactive terminal location data, the user preference data and the user preferred interaction mode data.

10. A new media cultural heritage interactive communication system based on digital twins, characterized in that: include: A first generating unit is used to construct a model based on the virtual heritage using the 3D scanning data of the cultural heritage to generate virtual data of the cultural heritage; A second generating unit inputs the cultural heritage virtual data and the user operation data into an augmented reality interaction model to generate virtual tour data, wherein the virtual tour data includes the cultural heritage virtual data and virtual guide data corresponding to the target user's tour location; The interactive control unit is used to send the virtual tour data to the experience terminal corresponding to the target user, so that the target user can perform a virtual tour.

Images